{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T09:09:23Z","timestamp":1788858563885,"version":"build-2803163510"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Egyptian Russian University"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Automated epileptic seizure detection from electroencephalogram (EEG) signals remains a critical challenge for real-world clinical deployment due to the complex, nonstationary, and multi-scale nature of neural dynamics. Existing deep learning approaches, including convolutional and transformer-based models, often fail to jointly capture spectral\u2013temporal dependencies while maintaining robustness across heterogeneous datasets and noisy clinical environments. In this work, we propose BrainXNet, a novel multi-scale spectro-temporal attention framework that unifies local feature extraction, frequency-aware representation learning, and global temporal modeling within a single architecture. The proposed model integrates (i) multi-scale convolutional pathways to capture transient and long-duration EEG patterns, (ii) a spectral attention module that dynamically emphasizes clinically relevant frequency bands, and (iii) a temporal transformer encoder for modeling long-range dependencies across EEG sequences. Extensive evaluations on two large-scale benchmark datasets, CHB-MIT and TUH Seizure Corpus, demonstrate that BrainXNet achieves state-of-the-art performance, reaching accuracies of 99.1% and 98.4%, respectively. Beyond in-dataset performance, the proposed framework exhibits strong cross-dataset generalization, maintaining over 94% accuracy in transfer settings, and demonstrates high robustness under noisy conditions. Ablation studies further confirm the complementary contributions of each architectural component. These results highlight the effectiveness of explicitly modeling multi-scale spectro-temporal dynamics for EEG analysis and position BrainXNet as a promising candidate for reliable, real-time clinical seizure detection systems. This work bridges the gap between high-performance experimental models and practical deployment in diverse healthcare environments.<\/jats:p>","DOI":"10.1038\/s41598-026-68506-6","type":"journal-article","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T08:24:03Z","timestamp":1788855843000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Frequency-aware transformer networks for robust and generalizable EEG-based seizure detection"],"prefix":"10.1038","volume":"16","author":[{"given":"Mostafa","family":"Gamal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mustafa","family":"Abdel-Wanes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"issue":"2","key":"68506_CR1","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1152\/physrev.00049.2021","volume":"104","author":"O Devinsky","year":"2024","unstructured":"Devinsky, O. et al. Cannabinoid treatments in epilepsy and seizure disorders. Physiol. Rev.104 (2), 591\u2013649 (2024).","journal-title":"Physiol. Rev."},{"key":"68506_CR2","doi-asserted-by":"publisher","first-page":"116677","DOI":"10.1016\/j.chaos.2025.116677","volume":"199","author":"B Hu","year":"2025","unstructured":"Hu, B., Wang, X., Ying, X. & Zhao, J. Dynamical modeling reveals the pivotal regulatory role of direct glutamatergic subthalamic-striatal projections in modulating basal ganglia activity during absence epilepsy. Chaos Solitons Fractals. 199, 116677 (2025).","journal-title":"Chaos Solitons Fractals"},{"key":"68506_CR3","doi-asserted-by":"publisher","first-page":"112059","DOI":"10.1016\/j.jtbi.2025.112059","volume":"602\u2013603","author":"B Hu","year":"2025","unstructured":"Hu, B., Guo, Y., Zhao, J. & Ma, X. Possible regulatory mechanisms of typical and atypical absence seizures through an equivalent projection from the subthalamic nucleus to the cortex: Evidence in a computational model. J. Theor. Biol.602\u2013603, 112059 (2025).","journal-title":"J. Theor. Biol."},{"key":"68506_CR4","doi-asserted-by":"publisher","first-page":"112366","DOI":"10.1016\/j.jtbi.2025.112366","volume":"621","author":"B Hu","year":"2025","unstructured":"Hu, B., Peng, J., Li, W., Xiao, Y. & Zhu, N. Deciphering the modulatory role of direct pedunculopontine nucleus-cortical circuitry in absence seizure dynamics: A computational study. J. Theoretical Biology. 621, 112366. https:\/\/doi.org\/10.1016\/j.jtbi.2025.112366 (2025).","journal-title":"J. Theoretical Biology"},{"issue":"11","key":"68506_CR5","doi-asserted-by":"publisher","first-page":"4434","DOI":"10.1111\/epi.18545","volume":"66","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y. et al. Self-supervised data-driven approach defines pathological high-frequency oscillations in epilepsy. Epilepsia66 (11), 4434\u20134450 (2025).","journal-title":"Epilepsia"},{"issue":"8","key":"68506_CR6","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1056\/NEJMra2301913","volume":"390","author":"E Donner","year":"2024","unstructured":"Donner, E., Devinsky, O. & Friedman, D. Wearable digital health technology for epilepsy. N. Engl. J. Med.390 (8), 736\u2013745 (2024).","journal-title":"N. Engl. J. Med."},{"key":"68506_CR7","unstructured":"Anon Epilepsy and seizures. National Institute of Neurological Disorders and Stroke."},{"key":"68506_CR8","doi-asserted-by":"crossref","unstructured":"Kumar, S. & Sharma, A. Advances in non-invasive EEG-based brain-computer interfaces: Signal acquisition, processing, emerging approaches, and applications. Signal Processing Strategies, pp.281\u2013310. (2025).","DOI":"10.1016\/B978-0-323-95437-2.00014-8"},{"key":"68506_CR9","doi-asserted-by":"crossref","unstructured":"Ahmed, N., Numan, M. O. A., Kabir, R., Islam, M. R. & Watanobe, Y. A robust deep feature extraction method for human activity recognition using a wavelet based spectral visualisation technique. Sensors, 24(13), p.4343. (2024).","DOI":"10.3390\/s24134343"},{"key":"68506_CR10","doi-asserted-by":"crossref","unstructured":"Urbina Fredes, S. et al. Enhanced epileptic seizure detection through wavelet-based analysis of EEG signal processing. Applied Sciences, 14(13), p.5783. (2024).","DOI":"10.3390\/app14135783"},{"issue":"15","key":"68506_CR11","doi-asserted-by":"publisher","first-page":"3981","DOI":"10.1140\/epjs\/s11734-025-01606-y","volume":"234","author":"ST Jonna","year":"2025","unstructured":"Jonna, S. T. & Natarajan, K. EEG signal processing in neurological conditions using machine learning and deep learning methods: a comprehensive review. Eur. Phys. J. Special Top. 234 (15), 3981\u20133999 (2025).","journal-title":"Eur. Phys. J. Special Top."},{"key":"68506_CR12","doi-asserted-by":"crossref","unstructured":"Ma, W. et al. A comprehensive review of deep learning in EEG-based emotion recognition: classifications, trends, and practical implications. PeerJ Computer Science, 10, p.e2065. (2024).","DOI":"10.7717\/peerj-cs.2065"},{"key":"68506_CR13","doi-asserted-by":"publisher","first-page":"66726","DOI":"10.1109\/ACCESS.2024.3399114","volume":"12","author":"KC Vidyasagar","year":"2024","unstructured":"Vidyasagar, K. C., Kumar, K. R., Sai, G. A., Ruchita, M. & Saikia, M. J. Signal to image conversion and convolutional neural networks for physiological signal processing: A review. Ieee Access.12, 66726\u201366764 (2024).","journal-title":"Ieee Access."},{"key":"68506_CR14","doi-asserted-by":"publisher","first-page":"17002","DOI":"10.1109\/ACCESS.2025.3532515","volume":"13","author":"S Khalfallah","year":"2025","unstructured":"Khalfallah, S., Peuch, W., Tlija, M. & Bouallegue, K. Exploring the effectiveness of machine learning and deep learning techniques for EEG signal classification in neurological disorders. IEEE Access. 13, 17002\u201317015 (2025).","journal-title":"IEEE Access."},{"issue":"2","key":"68506_CR15","first-page":"e70099","volume":"16","author":"J Chen","year":"2026","unstructured":"Chen, J. et al. A Review of EEG-Based Driver Fatigue Detection: Nonlinear Dynamics, Brain Networks, and Deep Learning Advances. Wiley Interdisciplinary Reviews: Data Min. Knowl. Discovery. 16 (2), e70099 (2026).","journal-title":"Wiley Interdisciplinary Reviews: Data Min. Knowl. Discovery"},{"key":"68506_CR16","doi-asserted-by":"publisher","first-page":"39249","DOI":"10.52202\/079017-1239","volume":"37","author":"G Wang","year":"2024","unstructured":"Wang, G. et al. Eegpt: Pretrained transformer for universal and reliable representation of eeg signals. Adv. Neural. Inf. Process. Syst.37, 39249\u201339280 (2024).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"68506_CR17","unstructured":"Khan, Q. Epilepsy seizure classification based on EEG signals using machine learning (Master\u2019s thesis, Q. Khan). (2024)."},{"key":"68506_CR18","unstructured":"Valipour, F., Valipour, Z., Garousi, M. & Khadem, A. Diagnosing epilepsy using entropy measures and embedding parameters of EEG signals. arXiv preprint arXiv:2401.07258. (2024)."},{"key":"68506_CR19","unstructured":"Kostoglou, K., M\u00fcller-Putz, G. R. & Graz, B. Optimizing time-varying autoregressive models for BCI applications. In 9th Graz Brain-Computer Interface Conference: Join Forces-Increase Performance: BCI 2024. (2024)."},{"key":"68506_CR20","doi-asserted-by":"crossref","unstructured":"Al Ghayab, H. R. et al. EEG based over-complete rational dilation wavelet transform coupled with autoregressive for motor imagery classification. Expert Systems with Applications, 269, p.126433. (2025).","DOI":"10.1016\/j.eswa.2025.126433"},{"key":"68506_CR21","doi-asserted-by":"crossref","unstructured":"Massar, H., Drissi, T. B., Nsiri, B. & Miyara, M. Advancements in Blind Source Separation for EEG Artifact Removal: A comparative analysis of Variational Mode Decomposition and Discrete Wavelet Transform approaches. Applied Acoustics, 228, p.110300. (2025).","DOI":"10.1016\/j.apacoust.2024.110300"},{"key":"68506_CR22","doi-asserted-by":"publisher","first-page":"120437","DOI":"10.1109\/ACCESS.2025.3574646","volume":"13","author":"Z Khan","year":"2025","unstructured":"Khan, Z., Dayal, A. & Kim, H. C. An Attention-Enhanced 3D-CNN Framework for Spectrogram-Based EEG Analysis in Epilepsy Detection. IEEE Access. 13, 120437\u2013120445 (2025).","journal-title":"IEEE Access."},{"key":"68506_CR23","doi-asserted-by":"crossref","unstructured":"Alharbi, N. S., Bekiros, S., Jahanshahi, H., Mou, J. & Yao, Q. Spatiotemporal wavelet-domain neuroimaging of chaotic EEG seizure signals in epilepsy diagnosis and prognosis with the use of graph convolutional LSTM networks. Chaos, Solitons & Fractals, 181, p.114675. (2024).","DOI":"10.1016\/j.chaos.2024.114675"},{"key":"68506_CR24","doi-asserted-by":"crossref","unstructured":"Abdulwahhab, A. H., Abdulaal, A. H., Al-Ghrairi, A. H. T., Mohammed, A. A. & Valizadeh, M. Detection of epileptic seizure using EEG signals analysis based on deep learning techniques. Chaos, Solitons & Fractals, 181, p.114700. (2024).","DOI":"10.1016\/j.chaos.2024.114700"},{"key":"68506_CR25","unstructured":"Favia, A. Deep learning for sleep state detection using cw doppler radar technology. (2021)."},{"key":"68506_CR26","unstructured":"Pratama, Y. Convolutional Neural Network Approaches for Spatial and Temporal Classification Using High-Resolution Sensor Data. (2025)."},{"key":"68506_CR27","doi-asserted-by":"crossref","unstructured":"Chen, J. et al. Enhancing unseen driver state detection: an EEG-based framework with brain connectivity and depthwise separable convolutional neural networks Vol. 124, p.110676 (Biomedical Signal Processing and Control, 2026).","DOI":"10.1016\/j.bspc.2026.110676"},{"issue":"1","key":"68506_CR28","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/TETCI.2025.3622647","volume":"10","author":"G Lan","year":"2025","unstructured":"Lan, G. et al. Deep neural networks internal representation via neuron community exploration. IEEE Trans. Emerg. Top. Comput. Intell.10 (1), 1038\u20131049 (2025).","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"68506_CR29","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, Y., Liu, D., Wang, Y. & Wang, Z. Automated recognition of epilepsy from EEG signals using a combining space\u2013time algorithm of CNN-LSTM. Scientific Reports, 13(1), p.14876. (2023).","DOI":"10.1038\/s41598-023-41537-z"},{"key":"68506_CR30","doi-asserted-by":"crossref","unstructured":"Vafaei, E. & Hosseini, M. Transformers in EEG Analysis: A review of architectures and applications in motor imagery, seizure, and emotion classification. Sensors, 25(5), p.1293. (2025).","DOI":"10.3390\/s25051293"},{"issue":"2","key":"68506_CR31","doi-asserted-by":"publisher","first-page":"e57","DOI":"10.1002\/brx2.57","volume":"2","author":"S Cong","year":"2024","unstructured":"Cong, S. et al. Comprehensive review of Transformer-based models in neuroscience, neurology, and psychiatry. Brain-X2 (2), e57 (2024).","journal-title":"Brain-X"},{"issue":"11","key":"68506_CR32","doi-asserted-by":"publisher","first-page":"5418","DOI":"10.1109\/JBHI.2022.3199206","volume":"26","author":"Y Sun","year":"2022","unstructured":"Sun, Y. et al. Continuous seizure detection based on transformer and long-term iEEG. IEEE J. Biomedical Health Inf.26 (11), 5418\u20135427 (2022).","journal-title":"IEEE J. Biomedical Health Inf."},{"key":"68506_CR33","doi-asserted-by":"crossref","unstructured":"Lan, G. et al. A deep neural network optimization framework based on optimal transport bridge feature selection and sparse representation (IEEE Transactions on Neural Networks and Learning Systems, 2026).","DOI":"10.1109\/TNNLS.2026.3678220"},{"key":"68506_CR34","doi-asserted-by":"crossref","unstructured":"Chen, J. et al. Entropy-informed deep residual network for nonlinear EEG dynamics in fine-grained driver state recognition p.115532 (Applied Soft Computing, 2026).","DOI":"10.1016\/j.asoc.2026.115532"},{"key":"68506_CR35","doi-asserted-by":"crossref","unstructured":"Lan, G. et al. Face swapping with adaptive exploration-fusion mechanism and dual en-decoding tactic. Expert Systems with Applications, 255, p.124822. (2024).","DOI":"10.1016\/j.eswa.2024.124822"},{"key":"68506_CR36","doi-asserted-by":"publisher","first-page":"0379","DOI":"10.34133\/cbsystems.0379","volume":"6","author":"J Yue","year":"2025","unstructured":"Yue, J. et al. Augmenting Electroencephalogram Transformer for Steady-State Visually Evoked Potential-Based Brain-Computer Interfaces. Cyborg Bionic Syst.6, 0379 (2025).","journal-title":"Cyborg Bionic Syst."},{"issue":"43","key":"68506_CR37","doi-asserted-by":"publisher","first-page":"e5426","DOI":"10.1002\/advs.202505426","volume":"12","author":"D Chen","year":"2025","unstructured":"Chen, D. et al. A Novel Transfer Learning-Based Hybrid EEG-fNIRS Brain-Computer Interface for Intracerebral Hemorrhage Rehabilitation. Adv. Sci.12 (43), e5426 (2025).","journal-title":"Adv. Sci."},{"key":"68506_CR38","doi-asserted-by":"publisher","first-page":"109284","DOI":"10.1016\/j.bspc.2025.109284","volume":"114","author":"L Chen","year":"2026","unstructured":"Chen, L. et al. Brain power mapping with optimized deep learning for EEG-based pilot fatigue detection. Biomed. Signal Process. Control. 114, 109284 (2026).","journal-title":"Biomed. Signal Process. Control"},{"key":"68506_CR39","doi-asserted-by":"publisher","first-page":"121542","DOI":"10.1016\/j.neuroimage.2025.121542","volume":"321","author":"X Huang","year":"2025","unstructured":"Huang, X. & Xu, S. Mitigating choice overload: The interactive effects of set size and overall preference revealed by hierarchical drift diffusion modeling and electroencephalography. NeuroImage321, 121542 (2025).","journal-title":"NeuroImage"},{"issue":"1","key":"68506_CR40","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/s13755-025-00370-6","volume":"13","author":"Y Qian","year":"2025","unstructured":"Qian, Y., Wang, Q., Yin, L. & Lu, A. CF-DTI: coarse-to-fine feature extraction for enhanced drug-target interaction prediction. Health Inform. Sci. Syst.13 (1), 55 (2025).","journal-title":"Health Inform. Sci. Syst."},{"issue":"5","key":"68506_CR41","doi-asserted-by":"publisher","first-page":"3352","DOI":"10.1109\/TETCI.2024.3523772","volume":"9","author":"Y Qian","year":"2025","unstructured":"Qian, Y., Su, L., Xu, M. & Tang, L. Enhanced Protein Secondary Structure Prediction Through Multi-View Multi-Feature Evolutionary Deep Fusion Method. IEEE Trans. Emerg. Top. Comput. Intell.9 (5), 3352\u20133363 (2025).","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"68506_CR42","doi-asserted-by":"publisher","first-page":"127462","DOI":"10.1016\/j.eswa.2025.127462","volume":"279","author":"Z Cheng","year":"2025","unstructured":"Cheng, Z. et al. The MLSE-SCAM architecture combines with the improved DRSN-TIC model for Raman spectroscopy small-sample data learning. Expert Syst. Appl.279, 127462 (2025).","journal-title":"Expert Syst. Appl."},{"key":"68506_CR43","doi-asserted-by":"publisher","first-page":"111952","DOI":"10.1016\/j.compag.2026.111952","volume":"250","author":"Z Liu","year":"2026","unstructured":"Liu, Z. et al. A self-supervised learning based method for fish disease diagnosis utilizing extremely limited samples. Comput. Electron. Agric.250, 111952 (2026).","journal-title":"Comput. Electron. Agric."},{"key":"68506_CR44","doi-asserted-by":"publisher","first-page":"112456","DOI":"10.1016\/j.jbiomech.2024.112456","volume":"179","author":"X Zhan","year":"2025","unstructured":"Zhan, X. et al. Differences between two maximal principal strain rate calculation schemes in traumatic brain analysis with in-vivo and in-silico datasets. J. Biomech.179, 112456 (2025).","journal-title":"J. Biomech."},{"key":"68506_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, H. & Li, H. Transformer-based EEG Decoding: A Survey. arXiv preprint arXiv:2507.02320. (2025).","DOI":"10.1109\/THMS.2026.3681097"},{"issue":"3","key":"68506_CR46","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1097\/WNP.0000000000000736","volume":"39","author":"MC Ng","year":"2022","unstructured":"Ng, M. C., Jing, J. & Westover, M. B. A primer on EEG spectrograms. J. Clin. Neurophysiol.39 (3), 177\u2013183 (2022).","journal-title":"J. Clin. Neurophysiol."},{"key":"68506_CR47","doi-asserted-by":"crossref","unstructured":"Peng, P., Song, Y., Yang, L. & Wei, H. Seizure prediction in EEG signals using STFT and domain adaptation. Frontiers in Neuroscience, 15, p.825434. (2022).","DOI":"10.3389\/fnins.2021.825434"},{"key":"68506_CR48","doi-asserted-by":"publisher","first-page":"1072801","DOI":"10.3389\/frai.2022.1072801","volume":"5","author":"AK Singh","year":"2023","unstructured":"Singh, A. K. & Krishnan, S. Trends in EEG signal feature extraction applications. Front. Artif. Intell.5, 1072801 (2023).","journal-title":"Front. Artif. Intell."},{"key":"68506_CR49","doi-asserted-by":"crossref","unstructured":"Prasanna, J. et al. Automated epileptic seizure detection in pediatric subjects of CHB-MIT EEG database\u2014a survey. Journal of Personalized Medicine, 11(10), p.1028. (2021).","DOI":"10.3390\/jpm11101028"},{"key":"68506_CR50","unstructured":"Dan, J. TUH Sz - Epilepsy benchmarks. SzCORE - Epilepsy Benchmarks."},{"key":"68506_CR51","doi-asserted-by":"crossref","unstructured":"Chen, J., Yuan, G. & Wei, C. Characterizing fatigue-related neural signatures via multi-band EEG features and a three-stage feature optimization strategy for driver fatigue detection (Measurement Science and Technology, 2026).","DOI":"10.1088\/1361-6501\/ae8d4b"},{"key":"68506_CR52","doi-asserted-by":"crossref","unstructured":"Yuvaraj, R., Baranwal, A., Prince, A. A., Murugappan, M. & Mohammed, J. S. Emotion recognition from spatio-temporal representation of EEG signals via 3D-CNN with ensemble learning techniques. Brain Sciences, 13(4), p.685. (2023).","DOI":"10.3390\/brainsci13040685"},{"key":"68506_CR53","doi-asserted-by":"crossref","unstructured":"Maliha, M. H., Lopa, A. R. & Chowdhury, M. H. May. Detection of Emotion from EEG Signal Using Deep Learning: Bi-LSTM and GRU. In 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT) (pp. 131\u2013136). IEEE. (2024).","DOI":"10.1109\/ICEEICT62016.2024.10534367"},{"key":"68506_CR54","doi-asserted-by":"crossref","unstructured":"Zhen, H. et al. A hybrid deep learning model and comparison for wind power forecasting considering temporal-spatial feature extraction. Sustainability, 12(22), p.9490. (2020).","DOI":"10.3390\/su12229490"},{"key":"68506_CR55","doi-asserted-by":"crossref","unstructured":"Konkar, A. & Qu, X. A Review of Transformer-Based and Hybrid Deep Learning Approaches for EEG Analysis. International Conference on Human-Computer Interaction (pp. 391-404). Springer, Cham. (2026)","DOI":"10.1007\/978-3-032-12660-3_29"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-68506-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-68506-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-68506-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T08:31:13Z","timestamp":1788856273000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-68506-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":55,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["68506"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-68506-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]},"assertion":[{"value":"5 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study exclusively used publicly available and de-identified EEG datasets (CHB-MIT and TUH Seizure Corpus). No new human participants were recruited, and no identifiable personal information was accessed by the authors. Therefore, according to institutional and national research guidelines, additional ethical approval and informed consent were not required for this study.","order":2,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"28076"}}